Word Folding: Taking the Snapshot of Words Instead of the Whole.
Jin-Dong KimJun'ichi TsujiiPublished in: IJCNLP (2004)
Keyphrases
- related words
- n gram
- english words
- word recognition
- unknown words
- word meaning
- word pairs
- word sense disambiguation
- word frequencies
- text corpus
- word segmentation
- word similarity
- word co occurrence
- lexical information
- syntactic categories
- linguistic knowledge
- multiword
- linguistic information
- co occurrence
- latent topics
- stop words
- query words
- word spotting
- distributional clustering
- keywords
- frequency counts
- word level
- chinese word segmentation
- handwritten words
- lexical features
- speech recognition systems
- language model
- automatic transcription
- noun phrases
- word meanings
- chinese text
- text classification
- short list
- spoken document retrieval
- word frequency
- training corpus
- compound words
- punctuation marks
- out of vocabulary
- numeral strings
- semantic relatedness between words
- printed text
- natural language
- character n grams
- bilingual dictionaries
- protein folding
- translation model
- word sense
- character recognition
- language specific
- keyword extraction
- handwritten documents
- concept space
- historical manuscripts
- natural language text
- part of speech
- semantic relations
- topic models
- text categorization